In this evaluation, there are total 3 data tables. We used the evaluation metrics implemented in OmicsEV package to evaluate these data tables. The sample and class information for each data table are shown in the table below.
| class | CDAP | MQ_ratio | paper |
|---|---|---|---|
| Basal | 11 | 11 | 11 |
| Her2 | 8 | 8 | 8 |
| LumA | 12 | 12 | 12 |
| LumB | 18 | 18 | 18 |
| None | 14 | 14 | 14 |
The detailed sample information is shown below.
| sample | class | batch | order |
|---|---|---|---|
| TCGA.AO.A12D | None | 1 | 1 |
| TCGA.C8.A131 | Basal | 1 | 2 |
| TCGA.AO.A12B | None | 1 | 3 |
| TCGA.E2.A10A | LumA | 1 | 4 |
| TCGA.C8.A130 | LumB | 1 | 5 |
| TCGA.C8.A138 | Her2 | 1 | 6 |
| TCGA.E2.A154 | LumA | 1 | 7 |
| TCGA.A8.A09I | LumB | 1 | 8 |
| TCGA.C8.A12L | Her2 | 1 | 9 |
| TCGA.A2.A0EX | LumA | 1 | 10 |
| TCGA.AN.A04A | None | 1 | 11 |
| TCGA.BH.A0AV | Basal | 1 | 12 |
| TCGA.A2.A0D0 | Basal | 1 | 13 |
| TCGA.C8.A12T | Her2 | 1 | 14 |
| TCGA.A8.A06Z | LumB | 1 | 15 |
| TCGA.A2.A0D1 | None | 1 | 16 |
| TCGA.A2.A0CM | Basal | 1 | 17 |
| TCGA.A2.A0YI | LumA | 1 | 18 |
| TCGA.A2.A0EQ | Her2 | 1 | 19 |
| TCGA.AR.A0TY | LumB | 1 | 20 |
| TCGA.AR.A0U4 | None | 1 | 21 |
| TCGA.BH.A0HP | LumA | 1 | 22 |
| TCGA.BH.A0EE | Her2 | 2 | 23 |
| TCGA.AO.A0J9 | None | 2 | 24 |
| TCGA.AN.A0FK | LumA | 2 | 25 |
| TCGA.AO.A0J6 | None | 2 | 26 |
| TCGA.A7.A13F | LumB | 2 | 27 |
| TCGA.A7.A0CE | Basal | 2 | 28 |
| TCGA.A2.A0YC | LumA | 2 | 29 |
| TCGA.AO.A0JC | None | 2 | 30 |
| TCGA.AR.A0TX | Her2 | 2 | 31 |
| TCGA.D8.A13Y | LumB | 2 | 32 |
| TCGA.A8.A076 | LumB | 2 | 33 |
| TCGA.AO.A126 | None | 2 | 34 |
| TCGA.C8.A12P | Her2 | 2 | 35 |
| TCGA.BH.A0C1 | LumA | 2 | 36 |
| TCGA.A2.A0EY | LumB | 2 | 37 |
| TCGA.AR.A1AW | LumB | 2 | 38 |
| TCGA.AR.A1AV | LumA | 2 | 39 |
| TCGA.C8.A135 | Her2 | 2 | 40 |
| TCGA.A2.A0EV | LumA | 2 | 41 |
| TCGA.AN.A0AM | LumB | 2 | 42 |
| TCGA.D8.A142 | Basal | 2 | 43 |
| TCGA.AN.A0FL | Basal | 3 | 44 |
| TCGA.AN.A0AS | LumA | 3 | 45 |
| TCGA.AR.A0TV | LumB | 3 | 46 |
| TCGA.C8.A12Z | Her2 | 3 | 47 |
| TCGA.AO.A0JJ | None | 3 | 48 |
| TCGA.AO.A0JE | None | 3 | 49 |
| TCGA.A2.A0T2 | Basal | 3 | 50 |
| TCGA.AN.A0AJ | LumB | 3 | 51 |
| TCGA.A7.A0CJ | LumB | 3 | 52 |
| TCGA.AO.A12F | None | 3 | 53 |
| TCGA.A2.A0YL | LumA | 3 | 54 |
| TCGA.A2.A0T7 | LumA | 3 | 55 |
| TCGA.C8.A12Q | Her2 | 3 | 56 |
| TCGA.A8.A079 | LumB | 3 | 57 |
| TCGA.E2.A159 | Basal | 3 | 58 |
| TCGA.A2.A0T3 | LumB | 3 | 59 |
| TCGA.A2.A0YD | LumA | 3 | 60 |
| TCGA.AR.A0TR | LumA | 3 | 61 |
| TCGA.AO.A03O | None | 3 | 62 |
| TCGA.AO.A12E | None | 3 | 63 |
| TCGA.A8.A06N | LumB | 3 | 64 |
| TCGA.A2.A0T1 | Her2 | 3 | 65 |
| TCGA.A2.A0YG | LumB | 3 | 66 |
| TCGA.E2.A150 | Basal | 3 | 67 |
| TCGA.A7.A0CD | LumA | 4 | 68 |
| TCGA.C8.A12W | LumB | 4 | 69 |
| TCGA.AN.A0AL | Basal | 4 | 70 |
| TCGA.A2.A0T6 | LumA | 4 | 71 |
| TCGA.AO.A0JM | None | 4 | 72 |
| TCGA.C8.A12V | Basal | 4 | 73 |
| TCGA.A2.A0D2 | Basal | 4 | 74 |
| TCGA.C8.A12U | LumB | 4 | 75 |
| TCGA.A8.A09G | Her2 | 4 | 76 |
| TCGA.C8.A134 | Basal | 4 | 77 |
| TCGA.A2.A0YF | LumA | 4 | 78 |
| TCGA.BH.A0E9 | LumA | 4 | 79 |
| TCGA.AR.A0TT | LumB | 4 | 80 |
| TCGA.AR.A1AQ | Basal | 4 | 81 |
| TCGA.A2.A0SW | LumB | 4 | 82 |
| TCGA.AO.A0JL | None | 4 | 83 |
| TCGA.A2.A0YM | Basal | 4 | 84 |
| TCGA.BH.A0C7 | LumB | 4 | 85 |
| TCGA.A2.A0SX | Basal | 4 | 86 |
The table below provides an overview about all the quantitative metrics generated in the evaluation. For each metric, the value of the best data table is highlighted. The detail of each metric can be found in corresponding section below.
| metric | CDAP | MQ_ratio | paper |
|---|---|---|---|
| #identified features |
10625 (0.5212) |
11368 (0.5576) |
10062 (0.4936) |
| #quantifiable features |
9465 (0.4643) |
9492 (0.4656) |
9227 (0.4526) |
| non_missing_value_ratio | 0.9505 | 0.9493 | 0.9397 |
| data_dist_similarity | 0.9851 | 0.9819 | 0.9188 |
| silhouette_width |
-0.1857 (0.8143) |
-0.3020 (0.6980) |
-0.4237 (0.5763) |
| pcRegscale |
0.0465 (0.9535) |
0.0000 (1.0000) |
0.0000 (1.0000) |
| complex_auc | 0.7486 | 0.7567 | 0.7438 |
| func_auc | 0.7655 | 0.7532 | 0.8227 |
| class_auc | 0.7730 | 0.7804 | 0.7434 |
| gene_wise_cor | 0.4203 | 0.4235 | 0.3784 |
| sample_wise_cor | 0.1916 | 0.2125 | 0.1783 |
The radar plot showing below is generated based on the data in the above overview table. To generate the radar plot, a metric is converted to a scale in which the value range is between 0 and 1 in a way that higher value indicates better data quality if necessary. The converted values are in parentheses.
The table below shows the number of identified proteins or genes for each data table. We take the proteins or genes filtered by 50% missing value as quantified proteins or genes. The values in parentheses are the percentage of proteins or genes identified or quantified based on the total number of proteins or genes (20386) in the study species.
| data table | #identified features | #quantifiable features |
|---|---|---|
| CDAP |
10625 (52.12%) |
9465 (46.43%) |
| MQ_ratio |
11368 (55.76%) |
9492 (46.56%) |
| paper |
10062 (49.36%) |
9227 (45.26%) |
Upset chart below showing overlap in proteins or genes identified in each data table. Numbers of identified proteins or genes shared between different data tables are indicated in the top bar chart and the specific data tables in each set are indicated with solid points below the bar chart. Total identifications for each data table are indicated on the left as ‘Set size’.
The figures below show the number of proteins or genes identified in each sample. Only when the quantification value of a gene or protein is not “NA” in a sample, this gene or protein is considered as identified in the sample. The samples from different batches are coded in different shapes and the samples from different classes are coded in different colors.
CDAPMQ_ratio
paper
The missing value distribution can give an overview of the percent of missing values of all proteins or genes in both the QC and experiment samples.
| data table | non_missing_value_ratio |
|---|---|
| CDAP | 0.9505 |
| MQ_ratio | 0.9493 |
| paper | 0.9397 |
CDAPMQ_ratio
paper
The boxplots show the protein or gene expression distribution across samples. X axis is sample ordered by input order. Y axis is log2 transformed protein or gene expression. The samples from different classes are coded in different colors.
CDAPMQ_ratio
paper
To quantify the normalization effect, for each pair of samples, perform an AUROC test to quantify the ability of feature abundance to distinguish the two samples and then generate a score based on 1-2*abs(AUROC-0.5), which will be 0 to 1, higher the better (no systematic difference between the two samples). The final metric for each data table is the median of scores from all sample pairs.
| data table | data_dist_similarity | n |
|---|---|---|
| CDAP | 0.9851 | 1953 |
| MQ_ratio | 0.9819 | 1953 |
| paper | 0.9188 | 1953 |
The density plots show the protein or gene expression distribution across samples. X axis is log2 transformed protein or gene expression. Y axis is density.
The silhouette width s(i) ranges from –1 to 1, with s(i) -> 1 if two clusters are separate and s(i) -> −1 if two clusters overlap but have dissimilar variance. If s(i) -> 0, both clusters have roughly the same structure. Thus, we use the absolute value |s| as an indicator for the presence or absence of batch effects.
| data table | silhouette_width |
|---|---|
| CDAP | -0.1857 |
| MQ_ratio | -0.3020 |
| paper | -0.4237 |
For each PC, we calculate Pearson’s correlation coefficient with batch covariate b:
ri =corr(PCi,b)
In a linear model with a single dependent, as is the case here for the PCs correlated to batch covariate, the coefficient of determination R2 is the squared Pearson’s correlation coefficient:
R2(PCi,b) = ri2
Then we estimate the significance of the correlation coefficient either with a t-test or a one-way ANOVA. The R2 value highlighted with red is significant (p-value <= 0.05).
| PC | CDAP | MQ_ratio | paper |
|---|---|---|---|
| 1 | 0.024 | 0.025 | 0.007 |
| 2 | 0.021 | 0.036 | 0.044 |
| 3 | 0.013 | 0 | 0.004 |
| 4 | 0 | 0.001 | 0.018 |
| 5 | 0.003 | 0.001 | 0.001 |
| 6 | 0.049 | 0.049 | 0.053 |
| 7 | 0.023 | 0.029 | 0.034 |
| 8 | 0.008 | 0.025 | 0 |
| 9 | 0.135 | 0.064 | 0.001 |
| 10 | 0.007 | 0.005 | 0.009 |
The fraction of variance explained for each PC:
| PC | CDAP | MQ_ratio | paper |
|---|---|---|---|
| 1 | 12.4 | 12.5 | 11.6 |
| 2 | 7.7 | 8.0 | 8.2 |
| 3 | 7.1 | 7.1 | 7.2 |
| 4 | 4.5 | 4.5 | 4.0 |
| 5 | 4.1 | 4.0 | 4.0 |
| 6 | 3.7 | 3.7 | 3.4 |
| 7 | 3.0 | 3.1 | 2.6 |
| 8 | 2.5 | 2.5 | 2.4 |
| 9 | 2.3 | 2.2 | 2.3 |
| 10 | 2.2 | 2.2 | 2.3 |
‘Scaled PC regression’, i.e. total variance of PCs which correlate significantly with batch covariate (FDR<0.05) scaled by the total variance of 10 PCs:
| data table | pcRegscale |
|---|---|
| CDAP | 0.0465 |
| MQ_ratio | 0.0000 |
| paper | 0.0000 |
In these figures, each column is a sample, each row is also a sample. The color indicates the correlation between samples. The samples are ordered by batches.
In these figures, each column is a sample, each row is also a sample. The color indicates the correlation between samples. The samples are ordered by batches.
CDAPMQ_ratio
paper
The table showing below is a summary of the evaluation. ‘diff’ is Cor(intra) - Cor(inter). ‘complex_auc’ is the AUROC value based on correlation of protein pairs from different groups.
| data table | InterComplex | IntraComplex | diff | complex_auc |
|---|---|---|---|---|
| CDAP | 0.0061 | 0.2261 | 0.2200 | 0.7486 |
| MQ_ratio | 0.0051 | 0.2331 | 0.2281 | 0.7567 |
| paper | 0.0153 | 0.2254 | 0.2101 | 0.7438 |
| RNA | 0.0247 | 0.1500 | 0.1252 | 0.6549 |
In this evaluation, each data table was used to build co-expression network. For a selected network and a selected function term (such as GO or KEGG), proteins/genes annotated to the term and also included in the network were defined as a positive protein/gene set and other proteins/genes in the network constituted the negative protein/gene set for the term. For a selected function term, we use some of the proteins/genes as the seed protein/gene, then we use random walk algorithm to calculate scores for other proteins/genes. A higher score of a protein/gene represents a closer relationship between the protein/gene and the seed proteins/genes. Finally, for each selected function term, we calculate an AUROC to evaluate the prediction performance.
| CDAP | MQ_ratio | paper | RNA | |
|---|---|---|---|---|
| Acute myeloid leukemia | 0.622 | 0.603 | 0.808 | 0.618 |
| Adherens junction | 0.593 | 0.649 | 0.682 | 0.539 |
| Adipocytokine signaling pathway | 0.602 | 0.626 | 0.758 | 0.594 |
| Alanine, aspartate and glutamate metabolism | 0.806 | 0.789 | 0.724 | 0.575 |
| Aldosterone-regulated sodium reabsorption | 0.792 | 0.685 | 0.881 | 0.634 |
| Alzheimers disease | 0.78 | 0.807 | 0.789 | 0.681 |
| Amino sugar and nucleotide sugar metabolism | 0.705 | 0.761 | 0.775 | 0.651 |
| Aminoacyl-tRNA biosynthesis | 0.811 | 0.718 | 0.799 | 0.735 |
| Amoebiasis | 0.666 | 0.691 | 0.784 | 0.606 |
| Amyotrophic lateral sclerosis (ALS) | 0.68 | 0.57 | 0.664 | 0.606 |
| Antigen processing and presentation | 0.698 | 0.785 | 0.843 | 0.833 |
| Apoptosis | 0.6 | 0.635 | 0.69 | 0.594 |
| Arachidonic acid metabolism | 0.69 | 0.714 | 0.626 | 0.746 |
| Arginine and proline metabolism | 0.632 | 0.773 | 0.683 | 0.668 |
| Arrhythmogenic right ventricular cardiomyopathy (ARVC) | 0.698 | 0.845 | 0.831 | 0.586 |
| Axon guidance | 0.552 | 0.653 | 0.592 | 0.607 |
| B cell receptor signaling pathway | 0.721 | 0.686 | 0.76 | 0.546 |
| Bacterial invasion of epithelial cells | 0.685 | 0.633 | 0.744 | 0.544 |
| Base excision repair | 0.776 | 0.627 | 0.633 | 0.727 |
| beta-Alanine metabolism | 0.681 | 0.753 | 0.748 | 0.591 |
| Bladder cancer | 0.67 | 0.642 | 0.604 | 0.553 |
| Calcium signaling pathway | 0.647 | 0.695 | 0.761 | 0.58 |
| Carbohydrate digestion and absorption | 0.723 | 0.67 | 0.905 | 0.775 |
| Cardiac muscle contraction | 0.835 | 0.855 | 0.919 | 0.705 |
| Cell adhesion molecules (CAMs) | 0.801 | 0.735 | 0.819 | 0.788 |
| Cell cycle | 0.716 | 0.704 | 0.82 | 0.751 |
| Chagas disease (American trypanosomiasis) | 0.64 | 0.622 | 0.779 | 0.56 |
| Chemokine signaling pathway | 0.611 | 0.673 | 0.669 | 0.592 |
| Chronic myeloid leukemia | 0.565 | 0.58 | 0.729 | 0.585 |
| Citrate cycle (TCA cycle) | 0.964 | 0.953 | 0.914 | 0.753 |
| Colorectal cancer | 0.582 | 0.558 | 0.611 | 0.576 |
| Complement and coagulation cascades | 0.909 | 0.918 | 0.901 | 0.874 |
| Cysteine and methionine metabolism | 0.674 | 0.659 | 0.663 | 0.632 |
| Cytokine-cytokine receptor interaction | 0.645 | 0.709 | 0.61 | 0.656 |
| Cytosolic DNA-sensing pathway | 0.708 | 0.668 | 0.676 | 0.651 |
| Dilated cardiomyopathy | 0.723 | 0.82 | 0.745 | 0.653 |
| DNA replication | 0.851 | 0.824 | 0.862 | 0.753 |
| Drug metabolism - other enzymes | 0.743 | 0.766 | 0.721 | 0.672 |
| ECM-receptor interaction | 0.895 | 0.906 | 0.855 | 0.765 |
| Endocytosis | 0.57 | 0.634 | 0.604 | 0.566 |
| Endometrial cancer | 0.628 | 0.662 | 0.686 | 0.556 |
| Epithelial cell signaling in Helicobacter pylori infection | 0.634 | 0.596 | 0.582 | 0.601 |
| ErbB signaling pathway | 0.64 | 0.604 | 0.624 | 0.573 |
| Fatty acid metabolism | 0.824 | 0.827 | 0.771 | 0.645 |
| Fc epsilon RI signaling pathway | 0.694 | 0.599 | 0.821 | 0.621 |
| Fc gamma R-mediated phagocytosis | 0.657 | 0.649 | 0.762 | 0.581 |
| Focal adhesion | 0.699 | 0.745 | 0.759 | 0.654 |
| Fructose and mannose metabolism | 0.739 | 0.753 | 0.807 | 0.629 |
| Galactose metabolism | 0.722 | 0.677 | 0.802 | 0.659 |
| Gap junction | 0.576 | 0.556 | 0.81 | 0.616 |
| Gastric acid secretion | 0.629 | 0.755 | 0.735 | 0.578 |
| Glioma | 0.514 | 0.662 | 0.552 | 0.533 |
| Glutathione metabolism | 0.662 | 0.549 | 0.65 | 0.615 |
| Glycerolipid metabolism | 0.675 | 0.656 | 0.592 | 0.612 |
| Glycerophospholipid metabolism | 0.677 | 0.67 | 0.628 | 0.591 |
| Glycine, serine and threonine metabolism | 0.666 | 0.715 | 0.697 | 0.739 |
| Glycolysis / Gluconeogenesis | 0.749 | 0.804 | 0.788 | 0.587 |
| Glyoxylate and dicarboxylate metabolism | 0.811 | 0.789 | 0.834 | 0.699 |
| GnRH signaling pathway | 0.632 | 0.587 | 0.725 | 0.654 |
| Hematopoietic cell lineage | 0.746 | 0.7 | 0.823 | 0.687 |
| Hepatitis C | 0.726 | 0.643 | 0.729 | 0.619 |
| Huntingtons disease | 0.803 | 0.79 | 0.895 | 0.745 |
| Hypertrophic cardiomyopathy (HCM) | 0.727 | 0.821 | 0.8 | 0.604 |
| Inositol phosphate metabolism | 0.584 | 0.633 | 0.565 | 0.659 |
| Insulin signaling pathway | 0.616 | 0.555 | 0.697 | 0.542 |
| Jak-STAT signaling pathway | 0.63 | 0.663 | 0.634 | 0.581 |
| Leishmaniasis | 0.723 | 0.664 | 0.779 | 0.684 |
| Leukocyte transendothelial migration | 0.779 | 0.729 | 0.796 | 0.652 |
| Long-term depression | 0.674 | 0.59 | 0.846 | 0.603 |
| Long-term potentiation | 0.567 | 0.703 | 0.807 | 0.611 |
| Lysine degradation | 0.827 | 0.776 | 0.66 | 0.606 |
| Lysosome | 0.738 | 0.772 | 0.768 | 0.589 |
| Malaria | 0.786 | 0.834 | 0.748 | 0.808 |
| MAPK signaling pathway | 0.587 | 0.614 | 0.651 | 0.515 |
| Melanogenesis | 0.62 | 0.573 | 0.886 | 0.637 |
| Melanoma | 0.515 | 0.572 | 0.668 | 0.625 |
| Metabolic pathways | 0.683 | 0.674 | 0.71 | 0.605 |
| mRNA surveillance pathway | 0.769 | 0.728 | 0.746 | 0.564 |
| mTOR signaling pathway | 0.763 | 0.637 | 0.654 | 0.588 |
| N-Glycan biosynthesis | 0.765 | 0.74 | 0.831 | 0.716 |
| Natural killer cell mediated cytotoxicity | 0.735 | 0.639 | 0.691 | 0.554 |
| Neurotrophin signaling pathway | 0.643 | 0.511 | 0.57 | 0.554 |
| NOD-like receptor signaling pathway | 0.662 | 0.651 | 0.738 | 0.578 |
| Non-small cell lung cancer | 0.613 | 0.53 | 0.777 | 0.571 |
| Notch signaling pathway | 0.502 | 0.639 | 0.668 | 0.569 |
| Nucleotide excision repair | 0.727 | 0.752 | 0.741 | 0.534 |
| Oocyte meiosis | 0.671 | 0.69 | 0.758 | 0.584 |
| Osteoclast differentiation | 0.725 | 0.638 | 0.726 | 0.601 |
| Oxidative phosphorylation | 0.939 | 0.967 | 0.937 | 0.777 |
| p53 signaling pathway | 0.63 | 0.703 | 0.582 | 0.738 |
| Pancreatic cancer | 0.589 | 0.628 | 0.572 | 0.582 |
| Pancreatic secretion | 0.766 | 0.753 | 0.842 | 0.555 |
| Parkinsons disease | 0.804 | 0.877 | 0.876 | 0.798 |
| Pathogenic Escherichia coli infection | 0.697 | 0.636 | 0.682 | 0.606 |
| Pathways in cancer | 0.558 | 0.55 | 0.667 | 0.534 |
| Pentose phosphate pathway | 0.811 | 0.871 | 0.725 | 0.72 |
| Peroxisome | 0.651 | 0.644 | 0.711 | 0.569 |
| Phagosome | 0.722 | 0.727 | 0.797 | 0.663 |
| Phosphatidylinositol signaling system | 0.565 | 0.534 | 0.621 | 0.628 |
| Porphyrin and chlorophyll metabolism | 0.571 | 0.74 | 0.593 | 0.562 |
| PPAR signaling pathway | 0.712 | 0.637 | 0.609 | 0.57 |
| Prion diseases | 0.655 | 0.712 | 0.9 | 0.663 |
| Progesterone-mediated oocyte maturation | 0.62 | 0.589 | 0.798 | 0.565 |
| Propanoate metabolism | 0.713 | 0.817 | 0.859 | 0.584 |
| Prostate cancer | 0.636 | 0.585 | 0.578 | 0.534 |
| Protein digestion and absorption | 0.877 | 0.947 | 0.859 | 0.852 |
| Protein processing in endoplasmic reticulum | 0.662 | 0.732 | 0.682 | 0.72 |
| Purine metabolism | 0.638 | 0.673 | 0.595 | 0.606 |
| Pyrimidine metabolism | 0.692 | 0.641 | 0.72 | 0.587 |
| Pyruvate metabolism | 0.828 | 0.766 | 0.842 | 0.507 |
| Regulation of actin cytoskeleton | 0.612 | 0.618 | 0.748 | 0.571 |
| Renal cell carcinoma | 0.606 | 0.551 | 0.689 | 0.555 |
| Rheumatoid arthritis | 0.62 | 0.679 | 0.765 | 0.607 |
| Ribosome | 0.969 | 0.976 | 0.954 | 0.83 |
| RIG-I-like receptor signaling pathway | 0.587 | 0.617 | 0.729 | 0.563 |
| Salivary secretion | 0.672 | 0.663 | 0.809 | 0.701 |
| Shigellosis | 0.574 | 0.673 | 0.738 | 0.555 |
| Small cell lung cancer | 0.601 | 0.708 | 0.7 | 0.596 |
| SNARE interactions in vesicular transport | 0.824 | 0.89 | 0.811 | 0.66 |
| Sphingolipid metabolism | 0.821 | 0.844 | 0.741 | 0.626 |
| Staphylococcus aureus infection | 0.841 | 0.794 | 0.938 | 0.907 |
| Systemic lupus erythematosus | 0.79 | 0.625 | 0.913 | 0.795 |
| T cell receptor signaling pathway | 0.625 | 0.613 | 0.734 | 0.604 |
| Tight junction | 0.598 | 0.632 | 0.784 | 0.514 |
| Toll-like receptor signaling pathway | 0.605 | 0.602 | 0.594 | 0.585 |
| Toxoplasmosis | 0.545 | 0.638 | 0.745 | 0.567 |
| Tryptophan metabolism | 0.697 | 0.713 | 0.692 | 0.63 |
| Type II diabetes mellitus | 0.626 | 0.683 | 0.755 | 0.593 |
| Ubiquitin mediated proteolysis | 0.605 | 0.577 | 0.649 | 0.601 |
| Valine, leucine and isoleucine degradation | 0.822 | 0.838 | 0.827 | 0.693 |
| Vascular smooth muscle contraction | 0.594 | 0.722 | 0.913 | 0.55 |
| VEGF signaling pathway | 0.606 | 0.56 | 0.767 | 0.571 |
| Vibrio cholerae infection | 0.67 | 0.765 | 0.84 | 0.657 |
| Viral myocarditis | 0.628 | 0.638 | 0.767 | 0.726 |
| Wnt signaling pathway | 0.594 | 0.659 | 0.595 | 0.603 |
CDAPMQ_ratio
paper
For each data table, machine learning models are built to predict sample class:LumA,LumB. In OmicsEV, random forest models are built and the models are evaluated using repeated 5 fold cross validation (20 times).
| dataSet | mean_ROC | median_ROC | sd_ROC |
|---|---|---|---|
| CDAP | 0.7730 | 0.7731 | 0.0196 |
| MQ_ratio | 0.7804 | 0.7755 | 0.0150 |
| paper | 0.7434 | 0.7431 | 0.0135 |
| RNA | 0.9899 | 0.9898 | 0.0038 |
CDAPMQ_ratio
paper
CDAPMQ_ratio
paper
| data table | n | n5 | n6 | n7 | n8 | gene_wise_cor |
|---|---|---|---|---|---|---|
| CDAP | 8671 | 3195 | 1682 | 593 | 92 | 0.4203 |
| MQ_ratio | 8524 | 3135 | 1648 | 581 | 79 | 0.4235 |
| paper | 8893 | 2824 | 1508 | 541 | 70 | 0.3784 |
CDAPMQ_ratio
paper
| data table | sample_wise_cor |
|---|---|
| CDAP | 0.1916 |
| MQ_ratio | 0.2125 |
| paper | 0.1783 |